AI Fundamentals

Cloud Platform: A cloud platform is a collection of services that can be used over the Internet instead of running it on computer or server.
Azure core categories: Compute, Storage, Networking, App Services.
Azure organization structure: Tenants -> Subscription -> Resource group and resources
Azure Tenant: It is an organization's home base and identity in Microsoft's cloud. The tenant includes users, groups, identities and policies for managing secure access.
Azure Subscription: A billing container for cloud resources. One tenant can contain one or many Azure subscriptions. Its tied with a payment method and sets boundaries for cost, quotas and access control.
Resource groups: Resource groups are folder that hold related Azure resources to manage them together.
Resource: Any individual service or object created in Azure. Each resource has resource type, configuration settings, unique resource name and ID and optional access controls.
Azure Portal: Open 'portal.azure.com' is a centrallized, web-based management user interface.
Host: Applications run on computers or environments. A host can be a virtual machine, provide compute, memory and networking to execute.
Scaling: To automatically or manually adjust the amount of computer power to use by adding or removing instances.
Instances: Copies of application running at the same time.
Types of scaling: Scale out or horizontal - to add more instances | Scale up or vertical - to increase CPU/memory on existing instance

AI Types of Data

When an agent queries the knowledge base, Foundry IQ uses agentic retrieval to break the question into subqueries, search multiple sources in parallel and return relevant, citation-backed information.
A foundry project builds and manages: Agents | Evaluations | Files and datasets | Vector indexes | Flows | Connections | Project-specific settings.

A client application is a program that a user interacts with on their device that sends requests to a server and displays the results.
An AI client application utilizes a model, data, and application logic to process and return results. The app logic is the code or workflow that sends requests to the model, receives the response, and processes and transforms results. The entire process is known as a client–server interaction.